Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jan 9;24(1):e54689.
doi: 10.15252/embr.202254689. Epub 2022 Nov 21.

Sphingosine-1-phosphate controls endothelial sphingolipid homeostasis via ORMDL

Linda Sasset  1   2 , Kamrul H Chowdhury  3 , Onorina L Manzo  1   2   4 , Luisa Rubinelli  1   2 , Csaba Konrad  3 , J Alan Maschek  3 , Giovanni Manfredi  2 , William L Holland  3 , Annarita Di Lorenzo  1   2
Affiliations

Sphingosine-1-phosphate controls endothelial sphingolipid homeostasis via ORMDL

Linda Sasset et al. EMBO Rep. .

Abstract

Disruption of sphingolipid homeostasis and signaling has been implicated in diabetes, cancer, cardiometabolic, and neurodegenerative disorders. Yet, mechanisms governing cellular sensing and regulation of sphingolipid homeostasis remain largely unknown. In yeast, serine palmitoyltransferase, catalyzing the first and rate-limiting step of sphingolipid de novo biosynthesis, is negatively regulated by Orm1 and 2. Lowering sphingolipids triggers Orms phosphorylation, upregulation of serine palmitoyltransferase activity and sphingolipid de novo biosynthesis. However, mammalian orthologs ORMDLs lack the N-terminus hosting the phosphosites. Thus, which sphingolipid(s) are sensed by the cells, and mechanisms of homeostasis remain largely unknown. Here, we identify sphingosine-1-phosphate (S1P) as key sphingolipid sensed by cells via S1PRs to maintain homeostasis. The increase in S1P-S1PR signaling stabilizes ORMDLs, restraining SPT activity. Mechanistically, the hydroxylation of ORMDLs at Pro137 allows a constitutive degradation of ORMDLs via ubiquitin-proteasome pathway, preserving SPT activity. Disrupting S1PR/ORMDL axis results in ceramide accrual, mitochondrial dysfunction, impaired signal transduction, all underlying endothelial dysfunction, early event in the onset of cardio- and cerebrovascular diseases. Our discovery may provide the molecular basis for therapeutic intervention restoring sphingolipid homeostasis.

Keywords: ORMDL; ceramide; endothelial dysfunction; serine palmitoyltransferase; sphingolipid.

PubMed Disclaimer

Figures

Figure 1
Figure 1. S1P acutely inhibits SPT activity
  1. A

    SPT activity and Western blot (WB) analysis of S1PR1 in S1pr1 f/f and S1pr1 ECKO endothelial cells after 4‐OHT (1 μM, 72 h) treatment (n = 8/group from three independent EC isolations/group; four mice/EC isolation).

  2. B–D

    LC–MS/MS quantification of Total (B) Ceramide, (C) Glucosylceramide, and (D) Sphingomyelin in S1pr1 f/f and S1Pr1 ECKO endothelial cells after 4‐OHT (1 μM, 72 h) treatment (n = 5/group from two independent EC isolations/group; four mice/EC isolation).

  3. E–G

    SPT activity in HUVEC in (E) absence or presence of S1P (300 nM, 30′); (F) absence or presence of C16:0‐ceramide (300 nM, 30′), and (G) absence or presence of C16:0‐ceramide (300 nM, 30′), in the presence of SKI II (1 μM, 1 h pre‐treatment). (n ≥ 6 biological replicates).

  4. H

    RT‐PCR for SphK1 and SphK2 in endothelial cells SphK1,2 f/f and SphK1,2 ECKO after 4‐OHT (1 μM, 72 h) treatment (n = 4 biological replicates).

  5. I

    SPT activity in SphK1,2 f/f and SphK1,2 ECKO after 4‐OHT (1 μM, 72 h) treatment in absence or presence of S1P (300 nM, 30′) or C16:0‐ceramide (300 nM, 30′) (n ≥ 5/group from three independent EC isolations/group; four mice/EC isolation).

  6. J

    Graphical abstract of the figures findings.

Data information: β‐ACTIN, loading control. 3[H]‐serine and palmitoyl‐CoA were used as substrates for SPT activity. Sphinganine—the reaction product—was separated in TLC (thin‐layer cromatography) and quantified. Data are expressed as mean ± SEM. *P ≤ 0.05; **P ≤ 0.01; ***P ≤ 0.001. Statistical significance was determined by unpaired t‐test (A‐H, K), and two‐way ANOVA with Tukey's post‐test (I). Source data are available online for this figure.
Figure EV1
Figure EV1. Ceramide and glucosylceramide levels are increased in S1pr1 ECKO mEC compared to S1pr1 f/f
  1. A–G

    LC–MS/MS quantification of total and specific (A–D) ceramides and (E–G) glucosylceramides in S1pr1 f/f and S1pr1 ECKO mEC after 4‐OHT (1 μM, 72 h) treatment (n = 5/group from two independent EC isolations/group; four mice/EC isolation).

Data information: Data are expressed as mean ± SEM. ***P ≤ 0.001. Statistical significance was determined by unpaired t‐test. Source data are available online for this figure.
Figure 2
Figure 2. S1P inhibits SPT activity via ORMDLs stabilization
  1. A, B

    (A) WB analysis of ORMDLs, NOGO‐B, SPTLC1, and SPTLC2 in HUVEC lysates in the absence or presence of S1P (300 nM, 30′) and (B) relative ORMDLs quantification (n = 7 biological replicates).

  2. C

    WB analysis of ORMDLs, SPTLC1, and SPTLC2 in HUVEC lysates in the absence or presence of C16:0‐ceramide (300 nM, 30′), with or without SKI II 1 μM, 1 h pre‐treatment.

  3. D

    SPT activity in HUVEC in the absence or presence of SEW2871 (300 nM, 15′) (n = 7 biological replicates).

  4. E, F

    (E) WB analysis of ORMDLs, SPTLC1, and SPTLC2 in HUVEC lysates in the absence or presence of SEW2871 (300 nM, 15′ and 30′) and (F) relative ORMDLs quantification (n = 6 biological replicates).

  5. G, H

    SPT activity and WB analysis of HUVEC treated with (G) siCTRL and siNOGO (40 nM, 72 h) (n ≥ 4/group), or with (H) siCTRL and siORMDL1/2/3 (40 nM, 72 h) (n = 4 biological replicates).

  6. I

    WB analysis of ORMDLs, P‐p38, p38, P‐JNK, JNK, P‐ERK, ERK, P‐AKT, and AKT in HUVEC lysates in the absence or presence of the indicated inhibitors, with or without S1P (300 nM, 30′).

  7. J

    Graphical abstract of the figures findings.

Data information: Western blot are representative of three or more independent biological replicates. β‐ACTIN, loading control. Data are expressed as mean ± SEM. *P ≤ 0.05; **P ≤ 0.01; ***P ≤ 0.001. Statistical significance was determined by unpaired t‐test (B, D), and two‐way ANOVA with Tukey's post‐test (F–H). Source data are available online for this figure.
Figure EV2
Figure EV2. S1P inhibits SPT activity via ORMDLs stabilization
  1. A

    RT‐PCR for Ormdl1, Ormdl2, and Ormdl3 in the presence or absence of S1P (300 nM, 30′) (n = 3 biological replicates).

  2. B

    Ormdl isoforms mRNA abundance determined subtracting the Ct of housekeeping 18S from the Ct of Ormdls (n = 8 biological replicates).

  3. C, D

    Quantification of © SPTLC1 and (D) SPTLC2 levels from Fig 1G.

  4. E, F

    (E) Western blot analysis for ORMDLs in HUVEC lysates treated with CHX (10 μM) for the indicated period of time, in the presence or absence of MG132 (10 μM) or EER1 (10 μM) and (F) relative quantification.

  5. G

    RT‐PCR for Ormdl1, Ormdl2, and Ormdl3 before and after independent silencing with the corresponding siRNA (40 nM, 72 h) (n = 4 biological replicates).

Data information: Western blot and RT‐PCR are representative of three or more independent biological replicates. β‐ACTIN, loading control. Data are expressed as mean ± SEM. ***P ≤ 0.001. Statistical significance was determined by two‐way ANOVA with Tukey's post‐test (C, D, F) and unpaired t‐test (A, G). Source data are available online for this figure.
Figure 3
Figure 3. ORMDLs are degraded via PHD‐mediated ubiquitination and proteasomal degradation
  1. A

    WB analysis of ORMDL3 (HA), SPTLC1, and SPTLC2 in HUVEC lysates expressing HA‐ORMDL3 and treated with cycloheximide (CHX, 10 μM) for the indicated period of time.

  2. B

    Prolyl hydroxylase consensus sequence in the three ORMDL isoforms.

  3. C–E

    WB analysis of ORMDLs, SPTLC1, and SPTLC2 in HUVEC lysates in absence or presence of S1P (300 nM, 30′) and with or without (C) DMOG (1 mM, 1 h pre‐treatment), (D) Eeyarestatin 1 (EER1, 10 μM, 1 h pre‐treatment), (E) MG132 (10 μM, 1 h pre‐treatment).

  4. F

    WB analysis of HA‐ORMDL3 and HA‐ORMDL3‐P137A in HUVEC lysates in the absence or presence of S1P (300 nM, 30′), DMOG (1 mM, 1 h), EER1 (10 μM, 1 h), and MG132 (10 μM, 1 h).

  5. G, H

    (G) WB analysis of HA‐ORMDL3 and HA‐ORMDL3‐P137A, SPTLC1, and SPTLC2 in HUVEC lysates treated with CHX (10 μM) for the indicated period of time, and (H) relative quantification.

  6. I

    WB analysis for Ubiquitin, HA, and GFP of HEK293T transfected with GFP‐ubiquitin and with the indicated HA‐ORMDL3 plasmid, and immunoprecipitated with HA antibody.

  7. J

    SPT activity in HUVEC expressing the HA‐ORMDL3 or HA‐ORMDL3‐P137A, and depleted of endogenous ORMDLs with siRNA, in the absence or presence of S1P (300 nM, 30′) (n ≥ 4 biological replicates).

  8. K

    Graphical abstract of the figure findings.

Data information: Western blot are representative of three or more independent biological replicates. β‐ACTIN, loading control. Data are expressed as mean ± SEM. *P ≤ 0.05; **P ≤ 0.01; ***P ≤ 0.001. Statistical significance was determined by two‐way ANOVA with Tukey's post‐test. Source data are available online for this figure.
Figure EV3
Figure EV3. ORMDL3 is hydroxylated at P137
  1. A

    HA‐ORMDL3 sequence. In green HA‐tag; in blue the peptides identified by MS; in red the prolines identified my MS.

  2. B

    Graphical representation of the peptides identified by MS and prolines localization.

  3. C

    Summary for the peptide containing P137.

  4. D

    Ion masses for the amino acids in the peptide.

  5. E

    Representative mass spectrometry showing the P137 hydroxylated.

Figure 4
Figure 4. S1P inhibits de novo sphingolipid biosynthesis via S1PRs
  1. A, B

    (A) SPT activity in S1pr1,3 f/f and S1pr1,2 ECKO murine endothelial cell (mEC) after 4‐OHT (1 μM, 72 h) and siS1PR3 (40 nM, 72 h) treatments, in the absence or presence of S1P (300 nM, 30′) (n ≥ 4/group from two independent EC isolations/group; four mice/EC isolation) and (B) relative WB analysis for S1PR1, ORMDLs, P‐AKT, and AKT.

  2. C–E

    LC–MS/MS quantification of Total (C) Ceramide, (D) Glucosylceramide, and (E) Sphingomyelin in S1pr1,3 f/f and S1Pr1,3 ECKO mEC (n ≥ 3/group from two independent EC isolations/group; four mice/EC isolation).

  3. F–H

    (F) SPT activity in HUVEC in the absence or presence of P‐FTY720 (100 nM, 30′) (n = 4 biological replicates). (G) WB analysis of ORMDLs and S1PR1 in HUVEC lysates in the absence or presence of P‐FTY720 (100 nM, 30′) and (H) relative ORMDLs quantification (n = 4 biological replicates).

  4. I

    Experimental procedure for the measurement of the de novo synthetized Ceramides and Glucosylceramides.

  5. J–M

    LC–MS/MS quantification of (J) total and (K) specific Ceramides, and of (L) total and (M) specific Glucosylceramides labeled with L‐Serine‐13C3, 15N in absence or presence of S1P (300 nM) (n ≥ 4/group from two independent EC isolations/group; four mice/EC isolation).

Data information: Western blots are representative of three or more independent biological replicates. Β‐ACTIN, loading control. Data are expressed as mean ± SEM. *P ≤ 0.05; **P ≤ 0.01; ***P ≤ 0.001. Statistical significance was determined by unpaired t‐test (C–F) and two‐way ANOVA with Tukey's post‐test (A, H, J–M). Source data are available online for this figure.
Figure EV4
Figure EV4. S1pr3 deletion leads to increased SPT activity and SL levels
  1. A, B

    (A) RT‐PCR for S1pr3 and (B) SPT activity in mEC after siCTRL or siS1PR3 treatment (40 nM, 72 h) (n = 4 biological replicates).

  2. C–E

    LC–MS/MS quantification of total (C) Ceramide, (D) Glucosylceramide, and (E) Sphingomyelin in murine endothelial cell (mEC) after siCTRL or siS1PR3 treatment (40 nM, 72 h) (n = 5/group from two independent EC isolations/group; 4 mice/EC isolation).

Data information: Data are expressed as mean ± SEM. *P ≤ 0.05; ***P ≤ 0.001. Statistical significance was determined by unpaired t‐test. Source data are available online for this figure.
Figure EV5
Figure EV5. Endothelial‐derived S1P inhibits SL biosynthesis via S1PR1,3
  1. A–E

    LC–MS/MS quantification of specific (A and B) ceramides and (C–E) glucosylceramides in S1pr1,3 f/f and S1Pr1,3 ECKO murine endothelial cell (mEC) after 4‐OHT (1 μM, 72 h) and siS1PR3 (40 nM, 72 h) treatments (n = 5/group from two independent EC isolations/group; four mice/EC isolation).

  2. F–J

    LC–MS/MS quantification of specific (F and G) ceramides and (H–J) glucosylceramides in Spns2 f/f and Spns2 ECKO mEC after 4‐OHT (1 μM, 72 h) treatment (n = 5/group from two independent EC isolations/group; four mice/EC isolation).

Data information: Data are expressed as mean ± SEM. *P ≤ 0.05; **P ≤ 0.01; ***P ≤ 0.001. Statistical significance was determined by unpaired t‐test. Source data are available online for this figure.
Figure 5
Figure 5. Endothelial‐derived S1P inhibits de novo sphingolipid biosynthesis
  1. A

    RT‐PCR for Spns2 in Spns2 f/f and Spns2 ECKO murine endothelial cell (mEC) after 4‐OHT (1 μM, 72 h) treatment (n = 4 biological replicates).

  2. B, C

    (B) Intracellular and (C) secreted S1P in Spns2 f/f and Spns2 ECKO mEC (n = 8 biological replicates).

  3. D

    SPT activity in Spns2 f/f and Spns2 ECKO , in the absence or presence of S1P (300 nM, 30′) (n ≥ 3/group from two independent EC isolations/group; four mice/EC isolation).

  4. E–G

    LC–MS/MS quantification of Total (E) Ceramide, (F) Glucosylceramide, and (G) sphingomyelin in Spns2 f/f and Spns2 ECKO mEC (n = 5/group from two independent EC isolations/group; four mice/EC isolation).

  5. H–K

    LC–MS/MS quantification of (H) total and (I) specific ceramides, and of (J) total and (K) specific Glucosylceramides labeled with L‐Serine‐13C3, 15N in the absence or presence of S1P (300 nM) (n ≥ 4/group from two independent EC isolations/group; four mice/EC isolation).

  6. L

    SPT activity in microsomes from lung of Spns2 f/f and Spns2 ECKO mice (n = 5 biological replicates).

Data information: β‐ACTIN, loading control. Data are expressed as mean ± SEM. *P ≤ 0.05; **P ≤ 0.01; ***P ≤ 0.001. Statistical significance was determined by unpaired t‐test (A–C, E–G, L), and two‐way ANOVA with Tukey's post‐test (D, H–K). Source data are available online for this figure.
Figure 6
Figure 6. Ceramide accrual leads to endothelial and mitochondrial disfunction
  1. A–C

    (A) WB analysis of P‐VEGFR2 (Y1175), VEGFR2, P‐IR (Y1150/1151), IR, P‐AKT (S473), AKT, P‐eNOS (S1176), and eNOS in Spns2 f/f and Spns2 ECKO murine endothelial cell (mEC) lysates in the absence or presence of VEGF (100 ng/ml, 2′) or Insulin (1 U/ml, 2′) and (B and C) relative quantification of the indicated phospho/total protein ratios (n ≥ 3 biological replicates).

  2. D, E

    (D) WB analysis of P‐VEGFR2 (Y1175), VEGFR2, P‐eNOS (S1176), and eNOS in Spns2 f/f and Spns2 ECKO mEC lysates in the absence or presence of VEGF (100 ng/ml, 2′), and in the absence or presence of Myriocin (300 nM) for the indicated time and (E) relative quantification of the indicated phospho/total protein ratios (n ≥ 3 biological replicates).

  3. F–I

    Vasodilation in response to (F) VEGF, (G) Insulin, (H) acetylcholine, and (I) SNP (Spns2 f/f , n = 3; Spns2ECKO, n = 3; Spns2ECKO + Myo, n = 4 biological replicates).

  4. J, K

    (J) Representative curves of OCR and (K) quantification of OCR metrics in Spns2 f/f and Spns2 ECKO mEC. Oligomycin (Oligo), uncoupler FCCP, rotenone, and antimycin A (Rot/AA) were added at the indicated times (n ≥ 9 biological replicates).

  5. L, M

    (L) Representative curves of ECAR and (M) quantification of ECAR metrics in Spns2 f/f and Spns2 ECKO murine endothelial cell (mEC). Oligomycin (Oligo), uncoupler FCCP, rotenone, and antimycin A (Rot/AA) were added at the indicated times (n ≥ 9 biological replicates).

  6. N–P

    (N) TMRM fluorescence, (O) mitochondrial area, and (P) number of mitochondria per cells, as quantified by TMRM and Hoechst fluorescence.

  7. Q, R

    (Q) Representative dot‐plot diagrams and ® relative quantification of Spns2 f/f and Spns2 ECKO mEC, in the absence or presence of Palmitate (300 μM, 16 h), stained with Annexin V and analyzed by FACS (n ≥ 5 biological replicates).

  8. S

    Graphical abstract of the figure findings.

Data information: Data are expressed as mean ± SEM. *P ≤ 0.05; **P ≤ 0.01; ***P ≤ 0.001; °°°P ≤ 0.001. *Spns2 f/f vs. Spns2 ECKO , °Spns2 ECKO vs. Spns2 ECKO  + Myo. Statistical significance was determined by two‐way ANOVA with Tukey's post‐test (B, C, E, F–I, R) and unpaired t‐test (K, M–P). Source data are available online for this figure.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Allende ML, Yamashita T, Proia RL (2003) G‐protein‐coupled receptor S1P1 acts within endothelial cells to regulate vascular maturation. Blood 102: 3665–3667 - PubMed
    1. Breslow DK, Collins SR, Bodenmiller B, Aebersold R, Simons K, Shevchenko A, Ejsing CS, Weissman JS (2010) Orm family proteins mediate sphingolipid homeostasis. Nature 463: 1048–1053 - PMC - PubMed
    1. Burg N, Swendeman S, Worgall S, Hla T, Salmon JE (2018) Sphingosine 1‐phosphate receptor 1 signaling maintains endothelial cell barrier function and protects against immune complex‐induced vascular injury. Arthritis Rheumatol 70: 1879–1889 - PMC - PubMed
    1. Cantalupo A, Di Lorenzo A (2016) S1P signaling and de novo biosynthesis in blood pressure homeostasis. J Pharmacol Exp Ther 358: 359–370 - PMC - PubMed
    1. Cantalupo A, Zhang Y, Kothiya M, Galvani S, Obinata H, Bucci M, Giordano FJ, Jiang XC, Hla T, Di Lorenzo A (2015) Nogo‐B regulates endothelial sphingolipid homeostasis to control vascular function and blood pressure. Nat Med 21: 1028–1037 - PMC - PubMed

Publication types